Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4381 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.8825. Min Act: -0.1700
Data Index: 6320104 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.6325. Min Act: -0.1700
Data Index: 4861812 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.5700. Min Act: -0.1700
Data Index: 4788052 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.4450. Min Act: -0.1700
Data Index: 2695236 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.4450. Min Act: -0.1700
Data Index: 8663311 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.3825. Min Act: -0.1700
Data Index: 7002066 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.2575. Min Act: -0.1700
Data Index: 5503237 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.2575. Min Act: -0.1700
Data Index: 3384876 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.1950. Min Act: -0.1700
Data Index: 1908640 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.1325. Min Act: -0.1700
Data Index: 2116733 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.0700. Min Act: -0.1700
Data Index: 5894614 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.0700. Min Act: -0.1700
Data Index: 491415 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8825. Min Range: -10.8825
Max Act: 9.9450. Min Act: -0.1700
Data Index: 8232833 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.0075. Min Act: -0.1700
Data Index: 8153050 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.0075. Min Act: -0.1700
Data Index: 1640930 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8825. Min Range: -10.8825
Max Act: 10.0075. Min Act: -0.1700
Data Index: 2630645 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8825. Min Range: -10.8825
Max Act: 9.9450. Min Act: -0.1700
Data Index: 1446606 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8825. Min Range: -10.8825
Max Act: 9.9450. Min Act: -0.1700
Data Index: 6495399 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8825. Min Range: -10.8825
Max Act: 9.9450. Min Act: -0.1700
Data Index: 5014058 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8825. Min Range: -10.8825
Max Act: 9.8825. Min Act: -0.1700
Data Index: 3078706 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19